© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39410
    Prev
    Next
    INDEX
    Explanations

    equivalent phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects occurrences of the word “equivalent,” especially where it’s used with numerical values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     delightfully
    -2.81
    癭
    -2.78
     dando
    -2.77
    1
    -2.69
    9
    -2.63
     serán
    -2.61
     shimmering
    -2.59
    3
    -2.58
     ort
    -2.52
     pivotal
    -2.50
    POSITIVE LOGITS
     strives
    2.77
     tries
    2.77
     undeniably
    2.70
     sizable
    2.63
     That
    2.58
     blatantly
    2.58
     Seems
    2.56
    陞
    2.55
    !!!!!
    2.55
     creates
    2.53
    Activations Density 0.008%

    No Known Activations